Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare a safe, non-destructive, closed-world read, so the description only needs to add context. It does add the result ordering and the fields returned (status, score, best dishes), but says nothing about empty results, pagination behavior, or how the radius interacts with the limit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, front-loaded with what is returned and followed by the one non-obvious semantic rule. Nothing repeats the schema and nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With six parameters, no output schema and 17% schema coverage, the description partially compensates by describing output fields and the AND semantics of `needs`. It is still not enough for a geo search tool since the `only` filter and the radius/limit relationship remain undefined.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 17%, but the description does the single most valuable thing: it pins down that `needs` is conjunctive (one dish must satisfy every need, not any). However, the ambiguous `only` enum (all/options/vegan) and the interaction of km with limit are left completely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence states a specific resource (restaurants), a scope (near a coordinate), an ordering (nearest first) and the returned fields (status, score, best dishes). That clearly distinguishes it from city-scoped siblings such as city_vegan_places, though it never names an alternative explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by geometry (use this for proximity queries) but there is no explicit when-to-use/when-not, and no mention of when search_places or place_vegan_options would be the better call. The second sentence guides how to pass `needs`, which is parameter guidance rather than tool-selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.